Elderly Care - Human Activity Recognition Using Radar with an Open Dataset and Hybrid Maps

Elderly Care - Human Activity Recognition Using Radar with an Open Dataset and Hybrid Maps

Zhang, Xinyu (University of Glasgow; University of Electronic Science and Technology of China)
Abbasi, Qammer H. (University of Glasgow)
Fioranelli, F. (TU Delft Microwave Sensing, Signals & Systems)
Romain, Olivier (Observatoire de Paris)
Le Kernec, Julien (University of Glasgow; University of Electronic Science and Technology of China)

Ur Rehman, Masood (editor)
Zoha, Ahmed (editor)

2022

Population ageing has become a severe problem worldwide. Human activity recognition (HAR) can play an important role to provide the elders with in-time healthcare. With the advantages of environmental insensitivity, contactless sensing and privacy protection, radar has been widely used for human activity detection. The micro-Doppler signatures (spectrograms) contain much information about human motion and are often applied in HAR. However, spectrograms only interpret magnitude information, resulting in suboptimal performances. We propose a radar-based HAR system using deep learning techniques. The data applied came from the open dataset “Radar signatures of human activities” created by the University of Glasgow. A new type of hybrid map was proposed, which concatenated the spectrograms amplitude and phase. After cropping the hybrid maps to focus on useful information, a convolutional neural network (CNN) based on LeNet-5 was designed for feature extraction and classification. In addition, the idea of transfer learning was applied for radar-based HAR to evaluate the classification performance of a pre-trained network. For this, GoogLeNet was taken and trained on the newly-produced hybrid maps. These initial results showed that the LeNet-5 CNN using only the spectrograms obtained an accuracy of 80.5%, while using the hybrid maps reached an accuracy of 84.3%, increasing by 3.8%. The classification result of transfer learning using GoogLeNet was 86.0%.

Convolutional neural network
Human activity recognition
Hybrid maps
Micro-Doppler
Radar
Transfer learning

http://resolver.tudelft.nl/uuid:22fdbb02-3230-4ed6-914c-146ee922d0a0

https://doi.org/10.1007/978-3-030-95593-9_4

Springer

2022-10-01

9783030955922

Body Area Networks. Smart IoT and Big Data for Intelligent Health Management - 16th EAI International Conference, BODYNETS 2021, Proceedings

16th EAI International Conference on Body Area Networks, BODYNETS 2021, 2021-12-25 → 2021-12-26, Virtual, Online

Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, 1867-8211, 420 LNICST

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2022 Xinyu Zhang, Qammer H. Abbasi, F. Fioranelli, Olivier Romain, Julien Le Kernec